Distinctive Image Features from Scale-Invariant Keypoints

@article{Lowe2004DistinctiveIF,
  title={Distinctive Image Features from Scale-Invariant Keypoints},
  author={David G. Lowe},
  journal={International Journal of Computer Vision},
  year={2004},
  volume={60},
  pages={91-110}
}
  • D. Lowe
  • Published 1 November 2004
  • Computer Science
  • International Journal of Computer Vision
This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with… Expand
View on Springer
cnbc.cmu.edu
12,355 Citations
Highly Influential Citations
628
Background Citations
1,234
Methods Citations
2,473
Results Citations
41

Supplemental Content

7:53
Video
SIFT - Distinctive Image Features from Scale-Invariant Keypoints (Part 2/2)
opentechtalk
15 February 2012
Presentation Slides
Distinctive Image Features from Scale-Invariant Keypoints
Presentation One
Presentation Two

12,355 Citations

Citation Type

Citation Type

Evaluation of Clustering Configurations for Object Retrieval Using SIFT Features
TLDR
Different configurations for clustering sets of keypoints according to their pose parameters are presented and evaluated: x and y coordinates location, scale and orientation based on Lowe’s approach. Expand
Relative scale method to locate an object in cluttered environment
TLDR
An efficient method to locate a three-dimensional object in cluttered environment by extracting features and matching them with reference features, clustering the matched features with generalized Hough transformation, and verifying clusters with spatial relations between the features is proposed. Expand
Geometric features extraction
TLDR
This chapter will discuss global and local features, and how to extract corners, edges, contours or salient regions, which are among the common features used in image analysis algorithms, and describe feature detection and a number of efficient descriptors, including SIFT, ASIFT, and SURF. Expand
Improved SIFT-Features Matching for Object Recognition
TLDR
An improvement of the original SIFT algorithm providing more reliable feature matching for the purpose of object recognition is proposed, and the main idea is to divide the features extracted from both the test and the model object image into several sub-collections before they are matched. Expand
Incorporating Background Invariance into Feature-Based Object Recognition
  • A. Stein, M. Hebert
  • Computer Science
  • 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1
  • 2005
TLDR
Improvements to the popular scale invariant feature transform (SIFT) are suggested which incorporate local object boundary information and the resulting feature detection and descriptor creation processes are invariant to changes in background. Expand
A Method to Enhance Homogeneous Distribution of Matched Features for Image Matching
TLDR
A coarse geometric transformation between two images is calculated, through which the detected feature points in one image are projected to the other image and matched to neighboring feature points of the fixed image within a pre-determined spatial distance. Expand
Shape Signature Matching for Object Identification Invariant to Image Transformations and Occlusion
TLDR
This paper introduces a novel shape matching approach for the automatic identification of real world objects in complex scenes, formed by a set of one dimensional signals called shape signatures, using the cross-correlation metric to gauge the degree of similarity between objects. Expand
Rotation invariant feature lines transform for image matching
Image matching has been one of the most fundamental issues in computer vision over the decades. We propose a method based on utilizing feature lines in order to achieve more robust image matching,… Expand
Sifting for better features to track: exploiting time and space
Feature detection and the matching and tracking of those features are common tasks in computer vision systems. Qualities like invariance to scale, rotation, and other transforms, robustness to… Expand
3D object recognition from cluttered and occluded scenes with a compact local feature
TLDR
Experimental results on three popular datasets demonstrate the effectiveness of the proposed technique which achieves the best results compared to the state of the art with all targets correctly recognized and their poses estimated. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 75 REFERENCES
Object recognition from local scale-invariant features
  • D. Lowe
  • Mathematics, Computer Science
  • Proceedings of the Seventh IEEE International Conference on Computer Vision
  • 1999
TLDR
Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds. Expand
Shape recognition with edge-based features
TLDR
An approach to recognizing poorly textured objects, that may contain holes and tubular parts, in cluttered scenes under arbitrary viewing conditions is described and a new edge-based local feature detector that is invariant to similarity transformations is introduced. Expand
Local feature view clustering for 3D object recognition
  • D. Lowe
  • Mathematics, Computer Science
  • Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
  • 2001
TLDR
This paper presents a method for combining multiple images of a 3D object into a single model representation that provides for recognition of 3D objects from any viewpoint, the generalization of models to non-rigid changes, and improved robustness through the combination of features acquired under a range of imaging conditions. Expand
Invariant Features from Interest Point Groups
TLDR
This work introduces a family of features which use groups of interest points to form geometrically invariant descriptors of image regions to ensure robust matching between images in which there are large changes in viewpoint, scale and illumi- nation. Expand
Reliable feature matching across widely separated views
  • A. Baumberg
  • Mathematics, Computer Science
  • Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662)
  • 2000
TLDR
A robust method for automatically matching features in images corresponding to the same physical point on an object seen from two arbitrary viewpoints that is optimised for a structure-from-motion application where it wishes to ignore unreliable matches at the expense of reducing the number of feature matches. Expand
Recognition Using Region Correspondences
  • R. Basri, D. Jacobs
  • Mathematics, Computer Science
  • International Journal of Computer Vision
  • 2004
TLDR
The new approach combines many of the advantages of the previous two approaches, while avoiding some of their pitfalls, and makes use of region information that reflects the true shape of the object. Expand
Probabilistic Models of Appearance for 3-D Object Recognition
TLDR
This work describes how to model the appearance of a 3-D object using multiple views, learn such a model from training images, and use the model for object recognition, and demonstrates that OLIVER is capable of learning to recognize complex objects in cluttered images, while acquiring models that represent those objects using relatively few views. Expand
Object class recognition by unsupervised scale-invariant learning
  • R. Fergus, P. Perona, Andrew Zisserman
  • Mathematics, Computer Science
  • 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
  • 2003
TLDR
The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals). Expand
Robust Wide Baseline Stereo from Maximally Stable Extremal Regions
TLDR
The wide-baseline stereo problem, i.e. the problem of establishing correspondences between a pair of images taken from different viewpoints, is studied and an efficient and practically fast detection algorithm is presented for an affinely-invariant stable subset of extremal regions, the maximally stable extremal region (MSER). Expand
Phase-Based Local Features
TLDR
The results show that the phase-based local feature leads to better performance when dealing with common illumination changes and 2-D rotation, while giving comparable effects in terms of scale changes. Expand
...
1
2
3
4
5
...